Neural network-based lifting load measurement method for automobile crane

Abstract

The invention relates to a neural network-based lifting load measurement method for an automobile crane, and aims to solve the technical problems of time and labor waste and inaccurate measurement result of measurement caused by the fact that the lifting load measurement process of the automobile crane is easily influenced by uncontrollable factors such as dynamic change of arm lever torque, mechanical friction at multiple positions and steel wire rope droop. According to the method, a crane boom mechanical model under the load action is established through structural characteristics and geometric parameters of a crane boom of the automobile crane, and the lifting load of the automobile crane under any environment, place and working condition can be quickly obtained through a microprocessor and a computer by utilizing a trained radial basis function neural network, so that the field actual measurement of the automobile crane is greatly saved, and the stability evaluation of the automobile crane is more convenient by obtaining the lifting load in real time; the real-time measurement of the lifting load is obtained by utilizing the pressure intensity and the elevation angle, the implementation is easy, the arrangement is convenient, and the cost is low; and the environmental interference and the system error are reduced, and the working efficiency is effectively improved.

Description

Technical field [0001] The invention belongs to the technical field of truck crane lifting load measurement, and in particular relates to a method for measuring the lifting load of a truck crane based on a neural network. Background technique [0002] Truck cranes are the main tools for lifting materials at stations, docks, and construction sites. The truck cranes currently in use have no mass measuring device. When lifting materials need to be measured, they often have to be weighed on a remote ground scale, which is time-consuming and increases operating costs. In some crane intelligent early warning systems, there is also a great demand for real-time weighing of hoisted loads. Therefore, it is imperative that truck cranes have metering functions that are not restricted by the environment and location, and can accurately and quickly measure in real time. [0003] Radial basis function neural network is a kind of feedforward neural network with excellent performance. Radial basis...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the technical problem that the measurement process of the hoisting load of the truck crane is easily affected by uncontrollable factors such as dynamic changes of the arm moment, multiple mechanical frictions, and wire rope sagging, resulting in time-consuming and labor-intensive measurement and inaccurate measurement results. A method for measuring the hoisting load of a truck crane based on a neural network. The invention uses the pressure of the hydraulic cylinder of the luffing cylinder and the elevation angle of the luffing oil cylinder to calculate the hoisting load of the truck crane, and uses the neural network method to realize the description and prediction of the lifting load, which can be used in hydraulic Real-time Measurement of Lifting Load of Truck Crane

Images